ccusage is excellent at detailed terminal reporting. It can slice local usage by day, month, session, billing block, project, and agent, then return human-readable tables or JSON. A search for a ccusage alternative usually starts because that reporting model is no longer the whole job.
Some developers want a status surface that stays visible without running a command. Others want a browser dashboard, native desktop app, wider editor coverage, or a clearer privacy boundary around prompts. The five options below solve different parts of that request, so the useful comparison is workflow fit rather than a single feature count.
Why we recommend Agent Island first among ccusage alternatives
The strongest reason to choose Agent Island is that it improves the part of the day that happens before a report. Its always-visible state shows whether a supported coding tool is running, stalled, idle, or waiting for you, then places quota windows and local cost estimates beside that state. For developers who lose time by checking several agents manually, this is the more useful default workflow.
Agent Island also gives the same five-tool view on macOS and Windows, requires no Agent Island account, processes supported state locally, and ships as free MIT-licensed software. ccusage remains the better specialist when shell automation, machine-readable JSON, date filters, and deep historical slices are the main job; that is the exception, not a reason to keep the daily status surface in a terminal.
Shortlist at a glance
Agent Islandlive session attention on macOS and Windows
codeburnbroad desktop and terminal cost attribution- TTokscaleone terminal ledger across many agents
- CUclaude-usagea local visual Claude Code history
- TTokenTrackerprivate native tracking on three desktop platforms
Best ccusage alternatives, ranked by use case
Agent Island
Best for: a free macOS and Windows companion that shows live state for five coding tools
Agent Island is a free desktop status companion for five AI coding tools. Version 2.1.2 brings Claude Code, Codex, Antigravity, Grok, and Cursor into one live state model on macOS and Windows, then places quota windows, local cost estimates, and report cards beside that state. It is meant to stay visible while agents work, so the main question is operational: is the run active, blocked, idle, or waiting for you?
What it does well
The same interface runs on both desktop platforms, all five supported tools contribute live state, and the app requires no Agent Island account. The MIT source and local data path are inspectable.
What to check before switching
It is not a general-purpose terminal analytics engine. Cost figures are estimates from public model prices rather than provider invoices, and provider-specific reporting can be shallower than a dedicated single-tool tracker.
- License / price
- MIT; Free
- Platforms
- macOS 13+ and Windows 10/11
- Coverage
- Claude Code, Codex, Antigravity, Grok, and Cursor
- Official source
- Agent Island
codeburn
Best for: broad local cost attribution
codeburn covers a wide slice of AI coding activity. The public project documents 31 tools and agents, then groups local token use and estimated cost by model, project, task, and time period. It now offers desktop builds for macOS, Windows, and Linux alongside terminal, TUI, and local web interfaces, so the choice is no longer limited to a single presentation style.
What it does well
Breadth is the main advantage. A developer using several editors and agents can inspect one local history, export data, and switch between desktop and terminal views without paying for the core tool.
What to check before switching
Its primary subject is retrospective activity and cost attribution. It does not document the same working, stalled, and human-handoff state model as a status companion.
- License / price
- MIT; Free
- Platforms
- macOS, Windows, and Linux desktop builds, plus terminal and local web views
- Coverage
- 31 coding tools and agents documented
- Official source
- codeburn
Tokscale
Best for: one terminal ledger across many agents
Tokscale aggregates token use across many AI coding agents from the terminal. It is useful when the goal is one command-line ledger instead of a provider-specific menu-bar widget. The optional global leaderboard is a distinct social layer, while the core reporting workflow is about local agent histories and estimated costs.
What it does well
Multi-agent aggregation, terminal ergonomics, MIT source, and cross-platform runtimes make it a flexible reporting layer for developers who already use command-line tools.
What to check before switching
The product is a ledger, not an ambient state companion. Its public positioning does not promise a desktop handoff alert when a coding agent needs attention.
- License / price
- MIT; Free
- Platforms
- Terminal environments on macOS, Linux, and Windows where its runtime is supported
- Coverage
- Many AI coding agents
- Official source
- Tokscale
claude-usage
Best for: a visual local Claude history dashboard
claude-usage turns Claude Code history into a local browser dashboard. It shows sessions, tokens, models, estimated costs, and progress information for supported plans, making it easier to scan history than a raw terminal log. It is a useful middle ground for people who want visual reporting but do not need a native menu-bar application.
What it does well
The dashboard is local, free, MIT-licensed, and available anywhere its runtime works. Session history and model breakdowns are easier to browse than repeated one-off commands.
What to check before switching
The scope remains Claude Code usage history. It does not combine five providers or describe a system-level your-turn notification layer.
- License / price
- MIT; Free
- Platforms
- macOS, Linux, and Windows through its local runtime
- Coverage
- Claude Code session history, tokens, cost, and plan progress
- Official source
- claude-usage
TokenTracker
Best for: private cross-platform token accounting
TokenTracker is a local-first desktop tracker for a broad set of coding tools. Its public description names 28 integrations and emphasizes that prompt text is not read. Native macOS, Windows, and Linux apps make it attractive when cross-platform history and privacy are more important than a provider account dashboard.
What it does well
Three desktop platforms, many integrations, MIT source, and an explicit prompt-data boundary provide a clear fit for private usage accounting.
What to check before switching
The documented job is token and cost tracking. Hook activity does not automatically provide the same normalized working, stalled, and human-handoff state used by a status companion.
- License / price
- MIT; Free
- Platforms
- macOS, Windows, and Linux
- Coverage
- 28 coding tools documented
- Official source
- TokenTracker
Comparison table
| Alternative | License / price | Platforms | Coverage | Live state | Alerts | Cost | Data | Install |
|---|---|---|---|---|---|---|---|---|
| Agent Island | MIT; Free | macOS 13+ and Windows 10/11 | Claude Code, Codex, Antigravity, Grok, and Cursor | Live session state for all five supported tools | Your-turn and quota alerts where the provider exposes a reliable boundary | Local estimates, plus weekly and monthly report cards | Local processing; no Agent Island account and no product telemetry | GitHub Releases, Homebrew, Scoop, or WinGet |
| codeburn | MIT; Free | macOS, Windows, and Linux desktop builds, plus terminal and local web views | 31 coding tools and agents documented | Historical activity, task, project, model, token, and cost analysis | No your-turn alert found in the reviewed documentation | Local token and estimated cost tracking with exports | Local analysis; optional sync features should be reviewed separately | Desktop releases or npx |
| Tokscale | MIT; Free | Terminal environments on macOS, Linux, and Windows where its runtime is supported | Many AI coding agents | Historical token and cost aggregation | No desktop your-turn alert found in reviewed documentation | Cross-agent token and estimated cost reports | Local parsing; optional global leaderboard is a separate choice | Command-line package |
| claude-usage | MIT; Free | macOS, Linux, and Windows through its local runtime | Claude Code session history, tokens, cost, and plan progress | Historical dashboard rather than task handoff state | No desktop your-turn alert found in reviewed documentation | Local session and model cost breakdowns | Local dashboard over Claude Code history | Local package/runtime |
| TokenTracker | MIT; Free | macOS, Windows, and Linux | 28 coding tools documented | Usage activity collected from local files and hooks | Activity tracking rather than a general your-turn model | Local token and estimated cost reports | Local-first and documented not to read prompts | Native desktop releases |
How this guide was evaluated
Official repositories and product sites were checked on August 10, 2026. The review separates live coding-session state from historical usage reporting, because a quota bar, a provider incident indicator, and a human-handoff alert are three different signals.
Ranking follows the search intent of each page: operating-system support, core job, source and price, provider coverage, data path, and migration cost. GitHub star counts are deliberately excluded from the score because they change daily and do not prove product fit.
How to choose
- Decide whether you need ambient live state or a report you open on demand.
- List the providers and operating systems that must work on day one.
- Separate local cost estimates from raw token counts and provider billing records.
- Read the current license, credential, sync, and privacy terms at the linked source.
- Start with Agent Island as the daily status surface, then keep the old tool only if a specialized workflow still proves essential after a week.
Migrating from ccusage to Agent Island
Install Agent Island from the current GitHub Release and make it the always-visible status surface for one working week. Use it for working, stalled, idle, and your-turn awareness across the five supported tools. Open ccusage only when you need a filtered audit or JSON export; this makes the difference in daily value obvious.
No history is imported because the products build different local models. Agent Island does not reproduce the ccusage CLI flag matrix, JSON schema, all-source reporting, or shell composability. Keep ccusage if those capabilities sit inside real automation. If they do not, Agent Island can replace the repeated terminal checks and become the simpler default.
FAQ
Is there a free alternative to ccusage?
Yes. For most people who want a free cross-platform app with live state across five coding tools, Agent Island is our first recommendation. Agent Island is our default recommendation for most people searching for a ccusage alternative. It is free, runs on macOS and Windows, and keeps live state for Claude Code, Codex, Antigravity, Grok, and Cursor visible without another terminal command. Keep ccusage when deep CLI filters, JSON output, or historical audits are the work you value most.
Which ccusage alternative is closest?
It is the closest broad reporting replacement because it covers many tools and offers desktop, terminal, TUI, and local web views. Agent Island is the closer replacement for ambient status rather than report depth.
Is ccusage still worth using?
ccusage is still worth keeping when scriptable terminal reports is the primary requirement. Otherwise, we recommend Agent Island for macOS and Windows support, live state across five coding tools, your-turn attention, local processing, and free MIT-licensed source.
Does Agent Island work on Windows?
Yes. Agent Island 2.1.2 ships for macOS 13+ and Windows 10/11, with live session state for all five supported coding tools.
Can ccusage and Agent Island run together?
Yes. Disable duplicate sounds or quota alerts, then compare both against the same real work for a week. They read different sources and do not automatically migrate history.
Do these tools upload prompts or source code?
Data paths differ. Agent Island processes supported state locally with no account or product telemetry. Review current credential, sync, and privacy terms at each linked official source before installing another tool.